Open an .acmf file in ACM and create a session.
AI agents invoke open_acm to trigger actions in ACM MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool launches an external application (ACM) and creates a new COM session, triggering an external operation beyond simple data reads or writes. It initiates a process/session in Aspen Custom Modeler, which constitutes executing an external operation. Severity is medium because misuse could open unintended files or consume system resources, but it doesn't directly delete data or move money.
From the tool's definition Open an .acmf file in ACM and create a session
Attacks that exploit this kind of access
Open an .acmf file in ACM and create a session. It is categorised as a Execute tool in the ACM MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the ACM MCP Server MCP server in PolicyLayer and add a rule for open_acm: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches ACM MCP Server. Nothing to install.
open_acm is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the open_acm rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for open_acm. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
open_acm is provided by the ACM MCP Server MCP server (pekosann/acm-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →